使用python爬取百度中的关于某个关键字的图片

百度图片的结果是滑动加载的, 并不是静态的页面, 需要不断下滑, 才能不断更新

下面案例的关键字是"奥运会"

import requests
import os
from bs4 import BeautifulSoup

base_url = "https://image.baidu.com/search/acjson?"

keyword = "奥运会"

params = {'tn': 'resultjson_com',
          'logid': '7293709351117530629',
          'ipn': 'rj',
                 'ct': 201326592,
                 'is': '',
                 'fp': 'result',
#                  'queryWord': keyword,
                 'cl': 2,
                 'lm': -1,
                 'ie': 'utf-8',
                 'oe': 'utf-8',
                 'adpicid': '',
                 'st': -1,
                 'z': '',
                 'ic': '',
                 'hd': '',
                 'latest': '',
                 'copyright': '',
#                  'word': keyword,
                 's': '',
                 'se': '',
                 'tab': '',
                 'width': '',
                 'height': '',
                 'face': 0,
                 'istype': 2,
                 'qc': '',
                 'nc': '1',
                 'fr': '',
                 'expermode': '',
                 'force': '',
                 'cg': '',
                 'pn': 30,  # 30 60 ...
                 'rn': 30,
                 'gsm': '1e',
                 '1623811985902': ''
          }

params['queryWord'] = keyword
params['word'] = keyword
headers = {'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.9',
           'Accept-Encoding': 'gzip, deflate, br',
           'Accept-Language': 'zh-CN,zh;q=0.9,en-US;q=0.8,en;q=0.7',
           'Cache-Control': 'max-age=0',
           'Connection': 'keep-alive',
           'sec-ch-ua': '"Google Chrome";v="89", "Chromium";v="89", ";Not A Brand";v="99"',
           'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/89.0.4389.82 Safari/537.36'}


# 在当前路径下，创建存放图片文件的文件夹
path = "./" + keyword
if(not os.path.exists(path)):
    os.makedirs(path)

# 下载多页
i = 0  # 文件编号
# 爬取5页或者是加载5次的图片
pages = 3
for page in range(pages):
    params['pn'] = (page + 1)*30
    response = requests.get(url=base_url, params=params, headers=headers)
    image_dict = response.json()
    image_list = image_dict["data"]
#     print(image_list)
    try:
        for image in image_list:  # 下载当前页所有图片
            url = image['middleURL'] # middleURL  hoverURL  
            img_response = requests.get(url=url, headers=headers)
            # 写入文件
            file_name = path+"/image"+str(i)+".jpg"
            with open(file_name, 'wb') as f:
                f.write(img_response.content)
            i += 1
#             print(f"下载{i}张")

    except Exception as e:
        # 因为每个json最后有个是空的字典, 所以要进行一下异常处理
        print("出错了:", e)
    print(f"已经爬取了{i}张图片")

这段代码可以直接将图片保存到本地(会自动创建一个以关键字命名的文件夹), 如下图所示